Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 296 insertions, 0 deletions

diff --git a/drivers/misc/ocxl/context.c b/drivers/misc/ocxl/context.c
new file mode 100644
index 000000000..33f25be46
--- /dev/null
+++ b/drivers/misc/ocxl/context.c
@@ -0,0 +1,296 @@
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright 2017 IBM Corp.
+#include <linux/sched/mm.h>
+#include "trace.h"
+#include "ocxl_internal.h"
+
+int ocxl_context_alloc(struct ocxl_context **context, struct ocxl_afu *afu,
+		struct address_space *mapping)
+{
+	int pasid;
+	struct ocxl_context *ctx;
+
+	ctx = kzalloc_obj(*ctx);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->afu = afu;
+	mutex_lock(&afu->contexts_lock);
+	pasid = idr_alloc(&afu->contexts_idr, ctx, afu->pasid_base,
+			afu->pasid_base + afu->pasid_max, GFP_KERNEL);
+	if (pasid < 0) {
+		mutex_unlock(&afu->contexts_lock);
+		kfree(ctx);
+		return pasid;
+	}
+	afu->pasid_count++;
+	mutex_unlock(&afu->contexts_lock);
+
+	ctx->pasid = pasid;
+	ctx->status = OPENED;
+	mutex_init(&ctx->status_mutex);
+	ctx->mapping = mapping;
+	mutex_init(&ctx->mapping_lock);
+	init_waitqueue_head(&ctx->events_wq);
+	mutex_init(&ctx->xsl_error_lock);
+	mutex_init(&ctx->irq_lock);
+	idr_init(&ctx->irq_idr);
+	ctx->tidr = 0;
+
+	/*
+	 * Keep a reference on the AFU to make sure it's valid for the
+	 * duration of the life of the context
+	 */
+	ocxl_afu_get(afu);
+	*context = ctx;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ocxl_context_alloc);
+
+/*
+ * Callback for when a translation fault triggers an error
+ * data:	a pointer to the context which triggered the fault
+ * addr:	the address that triggered the error
+ * dsisr:	the value of the PPC64 dsisr register
+ */
+static void xsl_fault_error(void *data, u64 addr, u64 dsisr)
+{
+	struct ocxl_context *ctx = data;
+
+	mutex_lock(&ctx->xsl_error_lock);
+	ctx->xsl_error.addr = addr;
+	ctx->xsl_error.dsisr = dsisr;
+	ctx->xsl_error.count++;
+	mutex_unlock(&ctx->xsl_error_lock);
+
+	wake_up_all(&ctx->events_wq);
+}
+
+int ocxl_context_attach(struct ocxl_context *ctx, u64 amr, struct mm_struct *mm)
+{
+	int rc;
+	unsigned long pidr = 0;
+	struct pci_dev *dev;
+
+	// Locks both status & tidr
+	mutex_lock(&ctx->status_mutex);
+	if (ctx->status != OPENED) {
+		rc = -EIO;
+		goto out;
+	}
+
+	if (mm)
+		pidr = mm->context.id;
+
+	dev = to_pci_dev(ctx->afu->fn->dev.parent);
+	rc = ocxl_link_add_pe(ctx->afu->fn->link, ctx->pasid, pidr, ctx->tidr,
+			      amr, pci_dev_id(dev), mm, xsl_fault_error, ctx);
+	if (rc)
+		goto out;
+
+	ctx->status = ATTACHED;
+out:
+	mutex_unlock(&ctx->status_mutex);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(ocxl_context_attach);
+
+static vm_fault_t map_afu_irq(struct vm_area_struct *vma, unsigned long address,
+		u64 offset, struct ocxl_context *ctx)
+{
+	u64 trigger_addr;
+	int irq_id = ocxl_irq_offset_to_id(ctx, offset);
+
+	trigger_addr = ocxl_afu_irq_get_addr(ctx, irq_id);
+	if (!trigger_addr)
+		return VM_FAULT_SIGBUS;
+
+	return vmf_insert_pfn(vma, address, trigger_addr >> PAGE_SHIFT);
+}
+
+static vm_fault_t map_pp_mmio(struct vm_area_struct *vma, unsigned long address,
+		u64 offset, struct ocxl_context *ctx)
+{
+	u64 pp_mmio_addr;
+	int pasid_off;
+	vm_fault_t ret;
+
+	if (offset >= ctx->afu->config.pp_mmio_stride)
+		return VM_FAULT_SIGBUS;
+
+	mutex_lock(&ctx->status_mutex);
+	if (ctx->status != ATTACHED) {
+		mutex_unlock(&ctx->status_mutex);
+		pr_debug("%s: Context not attached, failing mmio mmap\n",
+			__func__);
+		return VM_FAULT_SIGBUS;
+	}
+
+	pasid_off = ctx->pasid - ctx->afu->pasid_base;
+	pp_mmio_addr = ctx->afu->pp_mmio_start +
+		pasid_off * ctx->afu->config.pp_mmio_stride +
+		offset;
+
+	ret = vmf_insert_pfn(vma, address, pp_mmio_addr >> PAGE_SHIFT);
+	mutex_unlock(&ctx->status_mutex);
+	return ret;
+}
+
+static vm_fault_t ocxl_mmap_fault(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	struct ocxl_context *ctx = vma->vm_file->private_data;
+	u64 offset;
+	vm_fault_t ret;
+
+	offset = vmf->pgoff << PAGE_SHIFT;
+	pr_debug("%s: pasid %d address 0x%lx offset 0x%llx\n", __func__,
+		ctx->pasid, vmf->address, offset);
+
+	if (offset < ctx->afu->irq_base_offset)
+		ret = map_pp_mmio(vma, vmf->address, offset, ctx);
+	else
+		ret = map_afu_irq(vma, vmf->address, offset, ctx);
+	return ret;
+}
+
+static const struct vm_operations_struct ocxl_vmops = {
+	.fault = ocxl_mmap_fault,
+};
+
+static int check_mmap_afu_irq(struct ocxl_context *ctx,
+			struct vm_area_struct *vma)
+{
+	int irq_id = ocxl_irq_offset_to_id(ctx, vma->vm_pgoff << PAGE_SHIFT);
+
+	/* only one page */
+	if (vma_pages(vma) != 1)
+		return -EINVAL;
+
+	/* check offset validty */
+	if (!ocxl_afu_irq_get_addr(ctx, irq_id))
+		return -EINVAL;
+
+	/*
+	 * trigger page should only be accessible in write mode.
+	 *
+	 * It's a bit theoretical, as a page mmaped with only
+	 * PROT_WRITE is currently readable, but it doesn't hurt.
+	 */
+	if ((vma->vm_flags & VM_READ) || (vma->vm_flags & VM_EXEC) ||
+		!(vma->vm_flags & VM_WRITE))
+		return -EINVAL;
+	vm_flags_clear(vma, VM_MAYREAD | VM_MAYEXEC);
+	return 0;
+}
+
+static int check_mmap_mmio(struct ocxl_context *ctx,
+			struct vm_area_struct *vma)
+{
+	if ((vma_pages(vma) + vma->vm_pgoff) >
+		(ctx->afu->config.pp_mmio_stride >> PAGE_SHIFT))
+		return -EINVAL;
+	return 0;
+}
+
+int ocxl_context_mmap(struct ocxl_context *ctx, struct vm_area_struct *vma)
+{
+	int rc;
+
+	if ((vma->vm_pgoff << PAGE_SHIFT) < ctx->afu->irq_base_offset)
+		rc = check_mmap_mmio(ctx, vma);
+	else
+		rc = check_mmap_afu_irq(ctx, vma);
+	if (rc)
+		return rc;
+
+	vm_flags_set(vma, VM_IO | VM_PFNMAP);
+	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+	vma->vm_ops = &ocxl_vmops;
+	return 0;
+}
+
+int ocxl_context_detach(struct ocxl_context *ctx)
+{
+	struct pci_dev *dev;
+	int afu_control_pos;
+	enum ocxl_context_status status;
+	int rc;
+
+	mutex_lock(&ctx->status_mutex);
+	status = ctx->status;
+	ctx->status = CLOSED;
+	mutex_unlock(&ctx->status_mutex);
+	if (status != ATTACHED)
+		return 0;
+
+	dev = to_pci_dev(ctx->afu->fn->dev.parent);
+	afu_control_pos = ctx->afu->config.dvsec_afu_control_pos;
+
+	mutex_lock(&ctx->afu->afu_control_lock);
+	rc = ocxl_config_terminate_pasid(dev, afu_control_pos, ctx->pasid);
+	mutex_unlock(&ctx->afu->afu_control_lock);
+	trace_ocxl_terminate_pasid(ctx->pasid, rc);
+	if (rc) {
+		/*
+		 * If we timeout waiting for the AFU to terminate the
+		 * pasid, then it's dangerous to clean up the Process
+		 * Element entry in the SPA, as it may be referenced
+		 * in the future by the AFU. In which case, we would
+		 * checkstop because of an invalid PE access (FIR
+		 * register 2, bit 42). So leave the PE
+		 * defined. Caller shouldn't free the context so that
+		 * PASID remains allocated.
+		 *
+		 * A link reset will be required to cleanup the AFU
+		 * and the SPA.
+		 */
+		if (rc == -EBUSY)
+			return rc;
+	}
+	rc = ocxl_link_remove_pe(ctx->afu->fn->link, ctx->pasid);
+	if (rc) {
+		dev_warn(&dev->dev,
+			"Couldn't remove PE entry cleanly: %d\n", rc);
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ocxl_context_detach);
+
+void ocxl_context_detach_all(struct ocxl_afu *afu)
+{
+	struct ocxl_context *ctx;
+	int tmp;
+
+	mutex_lock(&afu->contexts_lock);
+	idr_for_each_entry(&afu->contexts_idr, ctx, tmp) {
+		ocxl_context_detach(ctx);
+		/*
+		 * We are force detaching - remove any active mmio
+		 * mappings so userspace cannot interfere with the
+		 * card if it comes back.  Easiest way to exercise
+		 * this is to unbind and rebind the driver via sysfs
+		 * while it is in use.
+		 */
+		mutex_lock(&ctx->mapping_lock);
+		if (ctx->mapping)
+			unmap_mapping_range(ctx->mapping, 0, 0, 1);
+		mutex_unlock(&ctx->mapping_lock);
+	}
+	mutex_unlock(&afu->contexts_lock);
+}
+
+void ocxl_context_free(struct ocxl_context *ctx)
+{
+	mutex_lock(&ctx->afu->contexts_lock);
+	ctx->afu->pasid_count--;
+	idr_remove(&ctx->afu->contexts_idr, ctx->pasid);
+	mutex_unlock(&ctx->afu->contexts_lock);
+
+	ocxl_afu_irq_free_all(ctx);
+	idr_destroy(&ctx->irq_idr);
+	/* reference to the AFU taken in ocxl_context_alloc() */
+	ocxl_afu_put(ctx->afu);
+	kfree(ctx);
+}
+EXPORT_SYMBOL_GPL(ocxl_context_free);